INDEX

Explanations

phrases related to discussions and statements of opinion

oai_token-act-pair · gpt-3.5-turbo

empty or blank sections in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 destro

-0.84

 redes

-0.72

 referen

-0.71

 conclud

-0.70

 advoc

-0.70

avorite

-0.70

ADRA

-0.69

 disadvant

-0.68

enegger

-0.66

 encount

-0.64

POSITIVE LOGITS

please

0.55

 âľ

0.55

println

0.55

?!

0.54

ËĪ

0.54

 partName

0.54

 Reck

0.53

0.52

ye

0.52

 dont

0.51

Activations Density 0.515%

phrases related to discussions and statements of opinion

empty or blank sections in the text

No Comments

No Known Activations